Add use <tunit> instead of <span> for Deepl translation

To avoid getting results like "... bla.&quot;</span>" ->
"... bla</span>.&quot;" from Deepl we need to set set splitting_tags
option to an element name (that's not as common as span).

lib/outlook/translators.ex

@@ -73,7 +73,7 @@ defmodule Outlook.Translators do
 
   defp prepare_article(tree) do
     # Logger.info "so far."
-    HtmlDocComponent.render_doc(%{tree: tree})
+    HtmlDocComponent.render_doc(%{tree: tree, tunit_tag: "tunit"})
     |> Phoenix.HTML.Safe.to_iodata()
     |> IO.iodata_to_binary()
   end
@@ -86,7 +86,7 @@ defmodule Outlook.Translators do
   def process_translation(translation, tunit_ids) do
     tunit_map = translation
     |> Floki.parse_fragment!
-    |> Floki.find("span.tunit")
+    |> Floki.find("tunit")
     |> Enum.map(fn {_,atts,cont} ->
       %TranslationUnit{
         nid: Enum.find(atts, fn {k,_} -> k == "nid" end) |> Tuple.to_list |> Enum.at(1),

lib/outlook/translators/deepl.ex

@@ -26,6 +26,8 @@ defmodule Outlook.Translators.Deepl do
       [
         {"source_lang", options.source_lang},
         {"target_lang", options.target_lang},
+        {"tag_handling", "xml"},
+        {"splitting_tags", "tunit"},
         {"file", content, {"form-data", [{:name, "file"}, {:filename, "datei.html"}]}, []}
       ]
     )

lib/outlook_web/components/html_doc_component.ex

@@ -9,17 +9,22 @@ defmodule OutlookWeb.HtmlDocComponent do
 
   attr :tree, :list, required: true
 
-  def render_doc(assigns) do
+  def render_doc(%{tunit_tag: _} = assigns) do
     ~H"""
       <%= for node <- @tree do %>
-        <.dnode node={node} />
+        <.dnode node={node} tunit_tag={@tunit_tag} />
       <% end %>
     """
   end
+  def render_doc(assigns) do
+    assigns
+    |> assign(:tunit_tag,  "span")
+    |> render_doc()
+  end
 
   def dnode(%{node: %{status: status}} = assigns) do
     ~H"""
-      <.dynamic_tag name="span" class="tunit" nid={@node.nid} {Map.get(@node.eph, :attributes, %{})}>
+      <.dynamic_tag name={@tunit_tag} class="tunit" nid={@node.nid} {Map.get(@node.eph, :attributes, %{})}>
         <%= @node.content |> raw %>
       </.dynamic_tag>
     """
@@ -27,9 +32,9 @@ defmodule OutlookWeb.HtmlDocComponent do
 
   def dnode(assigns) when assigns.node.type == :element do
     ~H"""
-      <.dynamic_tag name={@node.name} nid={@node.nid} {Map.get(@node.eph, :attributes, %{})}>
+      <.dynamic_tag name={@node.name} nid={@node.nid} {@node.attributes |> Map.merge(Map.get(@node.eph, :attributes, %{}))}>
         <%= for child_node <- @node.content do %>
-          <.dnode node={child_node} />
+          <.dnode node={child_node} tunit_tag={@tunit_tag} />
         <% end %>
       </.dynamic_tag>
     """